Doll with intelligent simulation eyes

Abstract

The invention relates to the technical field of dolls, in particular to a doll with intelligent simulation eyes, comprising a support body; the support body is provided with a simulation eye and an inflator pump; the simulation eyes are LCD (liquid crystal display) screens; the inflator pump is electrically connected with the LCD screen; an inflation cavity is formed in the supporting body; and the output end of the inflating pump is communicated with the inflating cavity. The inflation pump and the LCD screen are arranged on the supporting body, the inflation pump is electrically connected with the LCD screen, and the inflation state of the inflation pump and the display state of the LCD screen can be linked, so that the doll is rich in a brand new effect of flexibility.

Description

Technical Field

[0001] The present invention relates to the technical field of dolls, and particularly relates to a doll with intelligent simulation eyes. Background Art

[0002] In today's amusement and commercial scenarios, inflatable air membranes are widely used as a common facility. However, currently available inflatable air membranes on the market generally have the problems of single function and rigid form. Traditional air membranes only serve as a static display object, which can only provide basic space partitioning or appearance display functions, and cannot fully arouse the enthusiasm and interest of users to participate.

[0003] For example, in places such as amusement parks and theme parks, air membranes are often just simple architectural shapes, lacking interactivity with tourists. During festivals or special events, their fixed appearance is difficult to create a matching enthusiastic atmosphere and cannot meet people's pursuit of immersive and interesting experiences. Moreover, in daily use, such rigid air membranes cannot be flexibly adjusted according to different scenarios and needs, making their role in enhancing the play atmosphere extremely limited.

[0004] Due to the lack of dynamic function design, air membranes cannot show flexible changes, making it difficult to attract tourists to stay and participate for a long time. At the same time, their monotonous appearance cannot reflect the unique themes of different festivals and activities, resulting in insufficient atmosphere in the venue, greatly limiting the potential of air membrane products in enhancing user experience and commercial value. Based on this, there is an urgent practical need and important significance to develop a new type of inflatable air membrane that can have dynamic functions, be full of spirituality, thus significantly enhancing the play atmosphere and enriching the usage scenarios. Summary of the Invention

[0005] The purpose of the present invention is to address the above deficiencies in the prior art and provide a doll with intelligent simulation eyes.

[0006] The purpose of the present invention is achieved through the following technical solutions: A doll with intelligent simulation eyes includes a support body; the support body is provided with simulation eyes and an air pump; the simulation eyes are LCD screens; the air pump is electrically connected to the LCD screens; an inflatable cavity is provided inside the support body; the output end of the air pump is communicated with the inflatable cavity.

[0007] The present invention is further configured such that a PVC sheet is provided between the LCD screen and the support body.

[0008] The present invention is further configured such that the PVC sheet extends to be provided with a connecting seat; the connecting seat is detachably connected with a waterproof rear cover; an accommodating cavity is formed between the connecting seat and the waterproof rear cover; the LCD screen is arranged in the accommodating cavity; the PVC sheet is provided with a display channel communicating with the accommodating cavity.

[0009] The present invention is further configured such that a waterproof silica gel sheet is provided between the LCD screen and the connection base.

[0010] The present invention is further configured such that the PVC sheet is connected to the support body by means of glue and / or sewing.

[0011] The present invention is further configured such that the doll with intelligent simulation eyes further includes a rotating disk; the support body is arranged on the rotating disk.

[0012] The present invention is further configured to include the following steps:

[0013] S101. Obtain real-time data during the operation of the air pump to obtain dynamic correlation data of load fluctuation and power supply distribution; S102. Judge the output state of the air pump according to the dynamic correlation data and adjust the voltage output range of the air pump; S103. Judge the power supply stability of the LCD screen according to the adjusted voltage output range, and use a voltage stabilizing module to compensate and adjust the power supply line; S104. Adjust the installation structure of the LCD screen according to the internal pressure change of the inflation cavity; S105. Judge the power supply distribution stability according to the force data of the adjusted installation structure and generate an optimal power distribution model.

[0014] The present invention is further configured such that the obtaining of real-time data during the operation of the air pump to obtain dynamic correlation data of load fluctuation and power supply distribution includes: obtaining the current value, air pressure value and LCD screen power supply voltage value during the operation of the air pump through a sensor, processing the digital data by time series analysis, determining the frequency components and dynamic correlation intensity of load fluctuation, determining the influence coefficient of voltage stability on power supply distribution through regression analysis, and generating a classification model result by using a support vector machine algorithm.

[0015] The present invention is further configured such that the judging of the output state of the air pump according to the dynamic correlation data and adjusting the voltage output range of the air pump includes: extracting the output value from the dynamic correlation data set and comparing it with a preset threshold value. If it exceeds the preset range, obtain the target voltage output range value, adjust the voltage parameter of the air pump drive module, optimize the control parameter by using a random forest algorithm, and generate stable output state data.

[0016] The present invention is further configured such that the judging of the power supply stability of the LCD screen according to the adjusted voltage output range and using a voltage stabilizing module to compensate and adjust the power supply line includes: collecting the adjusted voltage output range and comparing it with the LCD screen power supply demand threshold value, extracting the characteristics of the insufficient stability state, obtaining the voltage stabilizing module adjustment parameter from a preset module, optimizing the deviation characteristics by using a support vector machine algorithm, updating the voltage stabilizing module control logic, and generating the voltage output data after stabilization.

[0017] The present invention is further configured such that the installation structure for adjusting the LCD screen according to the internal pressure change of the inflatable cavity includes: acquiring real-time data of the internal pressure of the inflatable cavity, processing the pressure change time series data through a convolutional neural network, determining the spatial extrusion quantization index, predicting the deformation amount using a regression algorithm, simulating the stress distribution through finite element analysis, verifying the stability of the adjustment scheme, and obtaining the optimized installation structure parameters;

[0018] The determination of the power supply distribution stability according to the force data of the adjusted installation structure and the generation of the optimal power distribution model include: analyzing the internal pressure change trend of the inflatable cavity and the force data, determining the fluctuation conditions and threshold ranges, classifying and training the historical data through a support vector machine, adjusting the hyperparameters to generate a classification model, and using logistic regression to analyze the historical power distribution data to generate the optimal power distribution model and output the optimized results.

[0019] The beneficial effects of the present invention: By providing an air pump and an LCD screen on the support body, and electrically connecting the air pump and the LCD screen, the present invention can link the inflation state of the air pump with the display state of the LCD screen, thereby giving the doll a new effect of being full of spirituality and agility. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The invention is further described with reference to the accompanying drawings. However, the embodiments in the drawings do not constitute any limitation to the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to the following drawings.

[0021] Figure 1 is a schematic structural diagram of the present invention;

[0022] Figure 2 is a schematic structural diagram of the cooperation between the support body and the simulation eyes of the present invention;

[0023] Figure 3 is a cross-sectional view of the cooperation between the support body and the simulation eyes of the present invention;

[0024] Figure 4 is an exploded structural diagram of the cooperation between the support body and the simulation eyes of the present invention;

[0025] Figure 5 is a flowchart of the present invention;

[0026] Wherein: 1, support body; 2, simulation eyes; 3, air pump; 4, PVC sheet; 41, connecting seat; 42, display channel; 5, waterproof back cover; 51, accommodating cavity; 6, waterproof silicone sheet; 7, LCD screen; 8, rotating disk. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0027] The present invention is further described in conjunction with the following embodiments.

[0028] As can be seen from Figures 1 to 5 Figures 1 to 5 , a doll with intelligent simulation eyes 2 according to this embodiment includes a support body 1; the support body 1 is provided with simulation eyes 2 and an air pump 3; the simulation eyes 2 are LCD screens 7; the air pump 3 is electrically connected to the LCD screens 7; an air inflation cavity is provided inside the support body 1; the output end of the air pump 3 is communicated with the air inflation cavity.

[0029] Specifically, in this embodiment, by arranging an air pump 3 and an LCD screen 7 on the support body 1 and electrically connecting the air pump 3 and the LCD screen 7, the inflation state of the air pump 3 can be linked with the display state of the LCD screen 7, so as to give the doll a new effect of being full of spirituality and agility.

[0030] Among them, the LCD screen 7 can realize Bluetooth, or directly import multiple effect videos, and has the function of switching effect videos; the circuit board control design and module of the LCD screen 7 can be synchronized with the air pump 3.

[0031] For a doll with intelligent simulation eyes 2 according to this embodiment, a PVC sheet 4 is provided between the LCD screen 7 and the support body 1. Through the above setting, it is convenient to connect and fix the LCD screen 7 and the support body 1.

[0032] For a doll with intelligent simulation eyes 2 according to this embodiment, the PVC sheet 4 extends with a connecting seat 41; the connecting seat 41 is detachably connected with a waterproof rear cover 5; a receiving cavity 51 is formed between the connecting seat 41 and the waterproof rear cover 5; the LCD screen 7 is arranged in the receiving cavity 51; the PVC sheet 4 is provided with a display channel 42 communicated with the receiving cavity 51. For a doll with intelligent simulation eyes 2 according to this embodiment, a waterproof silica gel sheet 6 is provided between the LCD screen 7 and the connecting seat 41. Through the above setting, it plays a waterproof role. For a doll with intelligent simulation eyes 2 according to this embodiment, the PVC sheet 4 is connected to the support body 1 by glue and / or sewing.

[0033] Specifically, first, the PVC sheet 4 and the fabric support body 1 are bonded together with glue. The glue material is oil-based glue. Then, colored silk threads of the same color as the PVC sheet 4 are configured and the PVC sheet 4 and the fabric support body 1 are sewn together. A waterproof silica gel sheet 6 is added between the PVC sheet 4 and the fabric support body 1 to play a waterproof role and a reinforcement role, prevent falling off during use, and ensure quality and safe use;

[0034] After assembling the LCD screen, it is coated with full glue to play a waterproof and anti-friction role.

[0035] Then place the LCD screen in the middle of the connecting base 41, and then use screws to fix the connecting base 41 to the waterproof back cover 5.

[0036] In addition, the space between the connecting base 41 and the waterproof back cover 5 is covered with potting glue to prevent water ingress and detachment. Additionally, a curved pocket is sewn at the sewing part of the nearby cloth cover and sealed with Velcro to prevent the connecting base 41 from falling off, playing a protective role.

[0037] For the doll with the intelligent simulation eyes 2 described in this embodiment, the doll with the intelligent simulation eyes 2 further includes a rotating disk 8; the support body 1 is arranged on the rotating disk 8. Through the above arrangement, the support body 1 can rotate.

[0038] The doll with the intelligent simulation eyes 2 described in this embodiment includes the following steps:

[0039] S101. Obtain the real-time data during the operation of the air pump 3 to obtain the dynamic correlation data of load fluctuation and power supply distribution;

[0040] S102. Judge the output state of the air pump 3 according to the dynamic correlation data and adjust the voltage output range of the air pump 3;

[0041] S103. Judge the power supply stability of the LCD screen 7 according to the adjusted voltage output range, and use a voltage stabilizing module to compensate and adjust the power supply line;

[0042] S104. Adjust the installation structure of the LCD screen 7 according to the change of the internal pressure of the inflatable cavity;

[0043] S105. Judge the power supply distribution stability according to the force data of the adjusted installation structure and generate an optimal power distribution model.

[0044] Specifically, during the R & D process, it was found that there was a problem of how to ensure the efficient inflation of the inflatable cavity while maintaining the stable operation of the LCD screen 7, both of which rely on the coordinated work of the air pump 3. In detail, the air pump 3, as the core power component, has its output end directly connected to the inflatable cavity inside the support body 1 and is responsible for injecting gas to form the morphological support of the doll. However, the air pump 3 also needs to establish an electrical connection with the LCD screen 7 to drive the display function of the simulation eyes 2, which leads to a unique business scenario problem: during the process of the doll changing from the initial flat state to the fully inflated and formed state, the working load of the air pump 3 will change dynamically, and this load fluctuation may interfere with its power supply output, thereby affecting the display stability of the LCD screen 7. For example, when the internal pressure of the inflatable cavity rises rapidly, the air pump 3 may tend to prioritize the air flow output in terms of power distribution, resulting in insufficient voltage or current supply to the LCD screen 7, causing phenomena such as the simulation eyes 2 flickering, going black, or having a response delay. Conversely, if the power demand of the LCD screen 7 is guaranteed first, the inflation efficiency may decrease, prolonging the doll forming time and affecting the user experience. In addition, the space inside the support body 1 is limited, and when the inflatable cavity expands, it may squeeze the installation position of the LCD screen 7, causing the screen to be deformed by force or having poor contact, further exacerbating the complexity of technical implementation. The core of this contradiction lies in: there is a functional correlation between the air pump 3 and the LCD screen 7, but the mismatch in their operation rhythm, resource requirements, and spatial layout forms a deep technical problem that urgently needs to be solved in the R & D process.

[0045] In this embodiment, by real-time monitoring the current, air pressure of the air pump 3, and the power supply voltage of the LCD screen 7, a dynamic correlation model between load fluctuation and power supply distribution is established. When the output of the air pump 3 exceeds the stable range, the voltage output is automatically adjusted, and the voltage stability risk of the LCD screen 7 is evaluated. When necessary, compensation is carried out through the voltage stabilization module. At the same time, the influence of the pressure change in the inflatable cavity on the installation position of the LCD screen 7 is considered, and the installation structure is optimized according to the extrusion degree. If the internal pressure affects the stability of power supply distribution, the support vector machine is used to classify and train the historical data to generate the optimal power distribution model. This method realizes the coordinated control of the air pump 3 and the LCD screen 7, improves the overall stability and reliability of the system, and provides a new idea for the collaborative management of devices in similar scenarios.

[0046] For a doll with intelligent simulation eyes 2 described in this embodiment, obtaining the real-time data during the operation of the air pump 3 to obtain the dynamic correlation data between load fluctuation and power supply distribution includes:

[0047] Obtain the current value, air pressure value, and the power supply voltage value of the LCD screen 7 when the air pump 3 is running through sensors, process the digital data using time series analysis, determine the frequency components and dynamic correlation strength of the load fluctuation, determine the influence coefficient of voltage stability on power supply distribution through regression analysis, and generate the classification model result using the support vector machine algorithm.

[0048] Specifically, it includes the following steps: Step 1: Obtain the real-time current value, air pressure value, and the power supply voltage value of the LCD screen 7 during the running period of the air pump 3 through sensors, and obtain digital data through analog-to-digital conversion. Step 2: Process the digital data using time series analysis to determine the characteristic parameters of the real-time current change, air pressure change, and voltage stability. Step 3: If the real-time current change exceeds the preset threshold, decompose the frequency components of the load fluctuation through Fourier transform to obtain the frequency-domain characteristic data. Step 4: According to the corresponding relationship between the frequency-domain characteristic data and the air pressure change, use correlation analysis to judge the dynamic correlation strength between the load fluctuation and the air pressure value. Step 5: Process the data of the power supply voltage and power supply distribution through regression analysis to determine the influence coefficient of voltage stability on power supply distribution. Step 6: Obtain the dynamic correlation strength and the influence coefficient, and use the support vector machine algorithm to classify the correlation relationship between the load fluctuation and the power supply distribution to obtain the classification model result. Step 7: Compare the classification model result with the real-time collected data to judge the dynamic correlation trend between the load fluctuation and the power supply distribution, and output the trend data.

[0049] Obtaining the real-time current value, air pressure value, and the supply voltage value of the LCD screen 7 during the operation of the air pump 3 through sensors and converting them into digital data is the basis of the entire analysis process. As an implementation, a current sensor can be used to monitor the working current of the motor of the air pump 3 in real time. For example, the current stabilizes at about 2.5A during normal operation, while the air pressure sensor records the air pressure output by the air pump, such as maintaining a standard value of 3 bar. In addition, a voltage sensor can detect the supply voltage of the LCD screen 7, such as a stable 5V. These data are converted into digital signals at a sampling rate of 100 times per second through an analog-to-digital converter, providing high-precision input for subsequent analysis. The advantage of this method is that it can capture subtle changes during operation, laying the foundation for anomaly detection. Using time series analysis to process these digital data can extract key characteristic parameters. Specifically, the change trend of the current over time can be observed. For example, at the initial stage of starting the air pump 3, the current may briefly rise to 3A and then fall back to 2.5A, indicating the characteristics of the motor starting load. The air pressure value may gradually increase from 0 bar to 3 bar, reflecting the dynamics of the inflation process. The voltage stability is manifested as the supply voltage fluctuation not exceeding ±0.1V. This analysis helps to identify the operating rules. For example, by judging the stationarity of the time series, it can be determined whether the device is in a normal state, thereby improving the accuracy of fault warning. When the real-time current change exceeds a preset threshold, such as exceeding 3.5A, the frequency components of the load fluctuation can be decomposed through Fourier transform. For example, during a certain operation, the current fluctuates frequently and with a large amplitude. The Fourier transform result shows that the main frequencies are concentrated at 10Hz and 50Hz, which may correspond to abnormal motor speed or load changes caused by air path blockage. This frequency-domain characteristic data can intuitively reflect the source of the fluctuation, and can more accurately locate the root cause of the problem compared with time-domain analysis, helping to optimize the device maintenance strategy. Further, according to the corresponding relationship between the frequency-domain characteristic data and the air pressure change, correlation analysis can be used to judge the dynamic correlation strength between the load fluctuation and the air pressure value. For example, assuming that the fluctuation at a frequency of 10Hz is highly correlated with the air pressure dropping to 2.5 bar, and the correlation coefficient reaches 0.9, it indicates that the load fluctuation may be caused by insufficient air pressure. The advantage of this analysis is to reveal the causal relationship between variables, providing a basis for subsequent classification. It should be noted that if the air pressure value is abnormal, it may be due to air path leakage or a decrease in the pump body efficiency. The problem direction can be quickly locked through the correlation strength. By processing the data of the supply voltage and the power supply distribution through regression analysis, the influence coefficient of voltage stability can be determined. For example, assuming that when the voltage drops from 5V to 4.8V, the LCD screen 7 shows flickering. The regression analysis shows that for every 0.1V drop in voltage, the power supply distribution efficiency decreases by 5%, and the influence coefficient is -0.05. This method can quantify the impact of voltage fluctuation on the system, providing data support for power supply design optimization and improving the overall stability. After obtaining the dynamic correlation strength and the influence coefficient, the support vector machine algorithm can be used to classify the correlation relationship between the load fluctuation and the power supply distribution.For example, the data is divided into two categories: "normal operation" and "abnormal fluctuation". When training the model, the input correlation strength is 0.9 and the influence coefficient is -0.05. The result shows that a certain operation is classified as "abnormal fluctuation". The advantage of this classification model is that it can automatically identify complex patterns, reduce the subjectivity of manual judgment, and improve the efficiency of real-time monitoring. By comparing the classification model results with the real-time collected data, the dynamic correlation trend between load fluctuation and power supply distribution can be judged. For example, the real-time data shows that the current fluctuation frequency is 50Hz, the air pressure drops to 2.5 bar, and the voltage is stable at 5V. The model predicts "abnormal fluctuation", and the trend data indicates that the abnormal air pressure may be the main cause. The benefit of this comparative analysis is that it can dynamically adjust the operation strategy, such as reducing the pump speed to relieve the insufficient air pressure and extending the equipment life. For example, as an extended solution, the threshold setting can be optimized by combining historical data. If the current exceeds 3.5A accompanied by a decrease in air pressure during multiple operations, the threshold can be dynamically adjusted to 3.3A for early warning. Further, if the voltage fluctuates frequently, a voltage stabilizing module can be added to ensure stable power supply distribution. This multi-faceted support implementation method not only improves the rigor of the analysis but also provides a direction for equipment optimization through trend data, ultimately achieving a double improvement in operation efficiency and reliability.

[0050] A doll with intelligent simulation eyes 2 according to this embodiment, which determines the output state of the air pump 3 according to the dynamic correlation data and adjusts the voltage output range of the air pump 3, includes:

[0051] Extract the output value from the dynamic correlation data set and compare it with a preset threshold. If it exceeds the preset range, obtain the target voltage output range value, adjust the voltage parameter of the driving module of the air pump 3, and optimize the control parameter by using the random forest algorithm to generate stable output state data.

[0052] Specifically, it includes the following steps: Step 1: Collect the real-time operation data of the air pump 3 through sensors to generate a dynamic correlation data set and obtain a preliminary output state. Step 2: Extract the output value of the air pump 3 from the dynamic correlation data set and compare it with a preset stable range threshold to determine the output exceeding state. Step 3: If it is determined through comparison that the output of the air pump 3 exceeds the preset stable range, obtain the target voltage output range value according to the predetermined interval table. Step 4: Adjust the voltage parameter of the driving module of the air pump 3 for the obtained target voltage output range value to obtain the adjusted output state data. Step 5: Perform secondary matching analysis on the adjusted output state data and the correlation data to determine whether the predetermined interval requirements are met. Step 6: If the secondary matching analysis determines that the predetermined interval is not reached, use the random forest algorithm to optimize the features of the dynamic correlation data set to obtain the optimized control parameter. Step 7: Update the voltage output range of the air pump 3 according to the optimized control parameter to generate the final stable output state data.

[0053] Collecting real-time data during the operation of the air pump 3 through sensors is the basis for generating a dynamic correlation dataset. As an implementation method, a current sensor, a pressure sensor, and a voltage sensor can be used to collect the operating current of the motor of the air pump 3, the output air pressure, and the supply voltage of the drive module respectively. For example, during a certain operation, the current sensor records that the current briefly rises from 2.5 A to 3 A when the motor starts, the pressure sensor shows that the air pressure gradually increases from 0 bar to 3 bar, and the voltage sensor detects that the supply voltage stabilizes at 5 V. These data are converted into digital signals at a high sampling rate through an analog-to-digital converter to form a dynamic dataset containing timestamps. The advantage of this method is that it can comprehensively capture the real-time state of the device operation, providing a reliable basis for subsequent analysis. Specifically, by extracting the output value from the dynamic correlation dataset and comparing it with a preset threshold, it can be determined whether the device deviates from the normal operating range. For example, the preset stable current range is 2.3 A to 2.7 A, and the standard air pressure value is 3 bar ± 0.2 bar. If the collected data during a certain time shows that the current reaches 3.2 A and the air pressure drops to 2.6 bar, it exceeds the preset range. This comparison can not only quickly locate the abnormality but also provide a direction for the adjustment strategy. It should be noted that the setting of the threshold can be optimized based on historical operation data. For example, through multiple tests, it is determined that the device efficiency decreases when the current exceeds 2.8 A, thereby improving the accuracy of the judgment. Further, when the output exceeds the stable range, the voltage can be adjusted according to a predetermined interval table. For example, the interval table stipulates that when the air pressure is lower than 2.8 bar, the target voltage range is 5.2 V to 5.5 V. Assuming the air pressure is 2.6 bar, the voltage of the drive module is adjusted from 5 V to 5.3 V, the motor power increases accordingly, and the air pressure gradually returns to 3 bar. The advantage of this adjustment is to optimize the operation state through voltage parameters, avoiding the device from being overloaded or having reduced efficiency due to load fluctuations. The adjusted output state data needs to be secondarily matched and analyzed with the dynamic correlation data to verify whether the expected result is achieved. For example, after adjustment, the current stabilizes at 2.6 A, the air pressure returns to 3 bar, and the voltage is 5.3 V, which matches the predetermined interval, indicating that the adjustment is effective. This secondary verification can ensure the reliability of the adjustment strategy and reduce the risk of misadjustment. As an implementation method, a time series graph can be drawn through a visualization tool to intuitively display the parameter change trends before and after adjustment, enhancing the transparency of the analysis. If the secondary match does not meet the expectation, a random forest algorithm needs to be used to optimize the features. For example, during a certain operation, the air pressure remains at 2.7 bar after adjustment and does not reach 3 bar. The random forest analyzes the historical data and finds that the current fluctuation frequency of 10 Hz is highly correlated with the insufficient air pressure, and the voltage stability has little impact on the air pressure. Therefore, the control parameters are optimized, and the motor speed is mainly adjusted instead of the voltage. This method generates a more accurate control strategy by exploring the deep patterns between data, improving the adjustment efficiency. Updating the voltage output range according to the optimized parameters is the key to achieving final stability.Specifically, if the random forest suggests reducing the rotation speed and maintaining the voltage at 5.1V, the updated data shows that the current is 2.5A, the air pressure is stable at 3 bar, and the fluctuation decreases. This update not only solves the current anomaly but also provides a reference for subsequent operations. Further, the threshold can be dynamically adjusted in combination with historical data. For example, the upper limit of the current can be optimized from 2.8A to 2.7A to give an early warning of potential risks. As an extended solution, trend analysis can be introduced to optimize the overall strategy. For example, it is found in multiple runs that the decrease in air pressure is related to the ambient temperature. A temperature sensor can be added to collect data, the model input can be adjusted, and the classification accuracy can be improved. This multi-faceted support method not only enhances the rigor of the solution but also optimizes the equipment life and operating efficiency through data-driven means. For example, a voltage stabilizer module is installed when the voltage fluctuates frequently to ensure stable power supply and reduce the flickering problem of the LCD screen 7. Finally, these measures jointly improve the reliability and performance of the inflator 3, providing strong support for real-time monitoring and maintenance.

[0054] For a doll with intelligent simulation eyes 2 described in this embodiment, the power supply stability of the LCD screen 7 is judged according to the adjusted voltage output range, and a voltage stabilizer module is used to compensate and adjust the power supply line, including:

[0055] Collect the adjusted voltage output range and compare it with the power supply demand threshold of the LCD screen 7, extract the characteristics of the insufficient stability state, obtain the adjustment parameters of the voltage stabilizer module from the preset module, optimize the deviation characteristics by using the support vector machine algorithm, update the control logic of the voltage stabilizer module, and generate the stabilized voltage output data.

[0056] Specifically, the adjusted voltage output data is collected and compared with the power supply demand threshold of the LCD screen 7 in real time to judge whether the voltage output exceeds the stable range, and a preliminary judgment result is obtained. According to the preliminary judgment result, the characteristics of the insufficient stability state are extracted. If there is insufficient stability, the initial adjustment parameters of the voltage stabilizer module are obtained from the preset module to determine the compensation adjustment direction. For the obtained compensation adjustment direction, the voltage parameters of the power supply line are dynamically adjusted by the voltage stabilizer module to obtain the adjusted power supply line data. The voltage output value is extracted from the adjusted power supply line data and subjected to a secondary matching analysis with the power supply demand threshold of the LCD screen 7 to judge whether the stable state requirement is met. If the secondary matching analysis determines that the stable state requirement is not met, the support vector machine algorithm is used to optimize the deviation characteristics between the voltage output and the power supply demand to obtain the optimized adjustment parameters. According to the optimized adjustment parameters, the control logic of the voltage stabilizer module is updated, and precise compensation adjustment is implemented on the power supply line to generate the stabilized voltage output data. The stabilized voltage output data is associated and verified with the operating state of the LCD screen 7, and the decision tree algorithm is used to analyze the matching degree between the voltage output and the power supply demand to determine the final adjustment result.

[0057] Specifically, by collecting the adjusted voltage output data and comparing it with the power supply demand threshold of the LCD screen 7 in real time, it is determined whether the voltage output exceeds the stable range and a preliminary determination result is obtained. The core of this process is real-time monitoring and threshold comparison. As an implementation method, data can be collected 10 times per second by the voltage sensor. Assuming that the power supply demand threshold of the LCD screen 7 is 5V±0.2V, if the voltage value collected at a certain time is 5.3V, it exceeds the stable range and is initially determined to be unstable. This real-time performance ensures that the system can respond quickly to abnormal fluctuations. For example, in the test of the LCD screen 7 on the production line, if the voltage suddenly jumps to 5.4V, the system can immediately mark it as abnormal, reducing the risk of subsequent misoperation. According to the preliminary determination result, the characteristics of the insufficient stability state are extracted. If there is insufficient stability, the initial adjustment parameters of the voltage stabilization module are obtained from the preset module to determine the compensation adjustment direction. Specifically, the characteristics of the insufficient stability state may be manifested as the frequency and amplitude of voltage fluctuations. For example, if the voltage repeatedly jumps between 5.1V and 5.3V within 5 seconds, the feature extraction can identify that the fluctuation amplitude is 0.2V and the frequency is 2 times per second. The initial adjustment parameters stored in the preset module may be empirical values based on historical data, such as setting the output gain of the voltage stabilizing module to +0.1V, and the direction is upward compensation. The advantage of this method is to quickly locate the problem and provide a preliminary solution to avoid flickering or damage to the LCD screen 7 due to continuous voltage imbalance. According to the obtained compensation adjustment direction, the voltage parameters of the power supply line are dynamically adjusted by the voltage stabilizing module to obtain the adjusted power supply line data. Further, the voltage stabilizing module can adopt a PID control strategy to adjust the output in real time according to the deviation. For example, the initial voltage is 5.3V and the target is 5V. The voltage stabilizing module adjusts the voltage to 5.1V by gradually reducing the output power. The adjusted power supply line data may be that the voltage is stable between 5.05V and 5.1V for 10 consecutive seconds. This dynamic adjustment improves the adaptability of the system, especially when the external load changes, it can effectively maintain power supply stability. The voltage output value is extracted from the adjusted power supply line data, and a secondary matching analysis is performed with the power supply demand threshold of the LCD screen 7 to determine whether the stable state requirements are met. As an implementation method, 10 groups of data are extracted, and the average value is 5.08V, which is within the range of 5V±0.2V, and it is considered that a stable state is reached. If a certain value is 5.25V, the secondary matching fails. This secondary verification improves the judgment accuracy. For example, in high brightness mode, the LCD screen 7 may be more sensitive to voltage, and the secondary matching can ensure that the display effect will not be affected by slight deviations. If the secondary matching analysis determines that the stable state requirement is not met, the support vector machine algorithm is used to optimize the deviation characteristics between the voltage output and the power supply demand to obtain the optimized adjustment parameters. Specifically, the support vector machine can analyze the time series data of the voltage deviation to find out the key influencing factors, such as voltage drift caused by temperature increase.Suppose the analysis finds that the deviation is positively correlated with the ambient temperature, and the optimization parameter may be adjusted to reduce the compensation amount by 0.05V. The advantage of this machine learning method is that it can discover hidden patterns and improve the intelligence of regulation. For example, in a high-temperature workshop in summer, the optimized parameters can significantly reduce overvoltage situations. Update the control logic of the voltage stabilization module according to the optimized regulation parameters, perform precise compensation regulation on the power supply line, and generate the stabilized voltage output data. Further, the control logic can be set to update the parameters once a minute. If the optimized parameter is to reduce by 0.05V, the voltage is adjusted from 5.25V to 5V, and the stabilized output data shows that the fluctuation does not exceed 0.1V within 30 consecutive seconds. This precise compensation ensures the reliability of long-term operation. For example, in an LCD screen 7 detection device that works continuously for 24 hours, it can effectively avoid failures caused by voltage cumulative deviation. Verify the association between the stabilized voltage output data and the operating state of the LCD screen 7, and use the decision tree algorithm to analyze the matching degree between the voltage output and the power supply demand to determine the final adjustment result. As an implementation method, the decision tree can judge the matching degree according to inputs such as voltage value, current load, and the brightness of the LCD screen 7. For example, when the voltage is 5V and the current is 0.5A, the brightness is normal and the matching degree is 95%; if the voltage is 5.3V and the brightness is abnormal, the matching degree drops to 70%. The advantage of this analysis method is that it is intuitive and highly interpretable, and can provide a basis for subsequent optimization. It should be noted that a high matching degree result can reduce screen flickering or color difference problems and improve the user experience. For example, in a medical display device, a high matching degree can also ensure the accuracy of diagnostic images. The above solution forms a complete voltage stabilization control logic from real-time monitoring to intelligent optimization. Through multi-level verification and algorithm support, it not only ensures the stability of the power supply for the LCD screen 7 but also improves the adaptive ability of the system. The actual effect of this method is particularly obvious in industrial scenarios, which can significantly reduce the equipment failure rate and extend the service life.

[0058] A doll with intelligent simulation eyes 2 described in this embodiment, the installation structure of the LCD screen 7 adjusted according to the internal pressure change of the inflatable cavity, includes:

[0059] Obtain the real-time data of the internal pressure of the inflatable cavity, process the pressure change time series data through a convolutional neural network, determine the spatial extrusion quantization index, use a regression algorithm to predict the deformation amount, simulate the stress distribution through finite element analysis, verify the stability of the adjustment scheme, and obtain the optimized installation structure parameters;

[0060] Obtain the real-time data of the internal pressure of the inflatable cavity collected by the sensor, calculate the amplitude and frequency of the pressure change through a preset time window, and obtain the pressure change characteristic value. Extract the dynamic parameters affecting the installation position from the pressure change characteristic value, process the time series data of the pressure change through a convolutional neural network, and determine the quantization index of the spatial extrusion. Calculate the extrusion degree value according to the quantization index of the spatial extrusion. If the extrusion degree value exceeds the preset threshold, predict the deformation amount of the installation position through a regression algorithm to obtain the deformation distribution data. Obtain the deformation distribution data, analyze the distribution of the stress points at the installation position of the LCD screen 7 through the pre-established geometric model of the installation structure, and determine the adjustment direction of the installation structure. Generate a parameter adjustment plan according to the adjustment direction, process the boundary conditions and material properties of the installation structure through an iterative optimization algorithm, and obtain the adjusted set of structural parameters. Extract the key geometric features from the adjusted set of structural parameters, simulate the stress distribution under the pressure change of the inflatable cavity through finite element analysis, and judge the stability of the adjustment plan. Obtain the stability judgment result, verify whether the adjustment plan meets the extrusion degree constraint through the preset convergence condition, and obtain the final optimized parameters of the installation structure.

[0061] Specifically, obtaining the real-time data of the internal pressure of the inflatable cavity collected by the sensor is the basis for optimizing the installation structure. As an implementation method, a highly sensitive pressure sensor can be used to continuously collect pressure data for 30 seconds at a sampling frequency of 100 Hz. Specifically, by setting a time window of 1 second, the amplitude and frequency of the pressure change are calculated to obtain the pressure change characteristic value. For example, if the pressure changes from 100 kPa to 110 kPa within 1 second, the amplitude is 10 kPa and the frequency is 1 Hz. Further, dynamic parameters affecting the installation position are extracted from the pressure change characteristic values. This can be achieved by processing the time series data of the pressure change through a convolutional neural network. Specifically, a network structure containing 3 convolutional layers and 2 fully connected layers is used, with the input being the pressure data for 30 seconds and the output being a quantization index representing the degree of spatial extrusion. For example, the network may output a value between 0 and 1, where 0.8 represents a higher degree of extrusion. It should be noted that when calculating the extrusion degree value based on the quantization index of spatial extrusion, a threshold can be set, such as 0.7. When the extrusion degree value exceeds this threshold, the deformation amount of the installation position needs to be predicted through a regression algorithm. As an implementation method, the support vector regression (SVR) algorithm can be used, with the input being the pressure change characteristics and the extrusion degree value, and the output being the predicted deformation amount of each point of the installation position. After obtaining the deformation distribution data, the stress point distribution at the installation position of the LCD screen 7 is analyzed through a pre-established geometric model of the installation structure. Specifically, a three-dimensional model can be established using finite element analysis software, including the LCD screen 7, the support structure, and the inflatable cavity. By applying the predicted deformation amount, the stress distribution of each part is analyzed to determine the stress concentration area, and then the adjustment direction of the installation structure is determined. When generating a parameter adjustment plan according to the adjustment direction, an iterative optimization algorithm can be used to process the boundary conditions and material properties of the installation structure. For example, the genetic algorithm is used to optimize the geometric parameters and material selection of the support structure to minimize stress concentration. Specifically, the population size can be set to 100 and the number of iterations can be set to 50, and a new set of structural parameters is generated through crossover and mutation operations. The key geometric features, such as the thickness and angle of the support structure, are extracted from the adjusted set of structural parameters. Then, the stress distribution under the pressure change of the inflatable cavity is simulated through finite element analysis. For example, the process of the pressure changing from 100 kPa to 120 kPa is simulated, and the stress changes of each part are analyzed. If the maximum stress is less than 70% of the material yield strength, it can be judged that the adjustment plan has good stability. Finally, the adjustment plan is verified whether it meets the extrusion degree constraint through a preset convergence condition. As an implementation method, the convergence condition can be set as: the change in the extrusion degree value is less than 0.05 in three consecutive iterations. When this condition is met, the final optimized parameters of the installation structure can be obtained. This method can effectively balance the structural stability and space utilization efficiency, and improve the installation quality and service life of the LCD screen 7 in the inflatable cavity environment.

[0062] Judging the stability of power supply distribution according to the adjusted force data of the installation structure and generating an optimal power distribution model, including:

[0063] Analyze the internal pressure change trend and force data of the inflatable cavity, determine the fluctuation conditions and threshold ranges, classify and train the historical data through a support vector machine, adjust the hyperparameters to generate a classification model, and use logistic regression to analyze the historical power distribution data to generate an optimal power distribution model and output the optimization results.

[0064] By obtaining the force data of the optimized installation position and combining with the operating state of the air pump 3, analyze the internal pressure change trend, judge whether it has an impact on the stability of power supply distribution, and obtain the preliminary impact evaluation result. Extract the correlation features between the internal pressure and power supply distribution from the preliminary impact evaluation result, use data analysis techniques to process the force data and historical data, and determine the specific conditions and threshold ranges for the occurrence of fluctuations. For the determined fluctuation conditions and threshold ranges, screen the power supply distribution records related to the internal pressure from the historical data to obtain the training data set. Classify and train the training data set through a support vector machine, adjust the hyperparameters and optimize the separating hyperplane to obtain a classification model that can distinguish stable and unstable states. According to the classification model, analyze the real-time force data and internal pressure input, judge whether the current power supply distribution is in a stable state, and output the stability classification result. Combine the classification result with the power distribution demand, and perform regression analysis on the historical power distribution data through the logistic regression algorithm to obtain the initial parameters of the optimal power distribution model. By inputting the internal pressure and force data into the optimal power distribution model in real time, adjust the power distribution plan and output the final optimized result of power supply distribution.

[0065] Specifically, by combining the optimized force data at the installation position with the operating state of the air pump 3, the internal pressure change trend can be analyzed in depth. This analysis helps to determine whether the pressure fluctuation affects the stability of power supply distribution, thereby obtaining a preliminary impact assessment result. As an implementation method, multiple pressure sensors can be set at different positions inside the inflation cavity to monitor the pressure change in real time. For example, install a pressure sensor at the top, bottom, and side of the cavity respectively, and set the data acquisition frequency to 10 times per second, so that the pressure fluctuation can be accurately captured. Specifically, time series analysis methods can be used to process the pressure data. For example, the moving average method is used to smooth short-term fluctuations, and then the autoregressive model is used to predict the pressure trend. In this way, abnormal pressure change patterns can be identified, such as sudden pressure drops or continuous pressure increases. Further, by performing correlation analysis on the pressure data and the power supply distribution data, potential correlations can be found. For example, when the pressure suddenly rises by 5%, it is observed that the power supply power fluctuation increases by 2%. Such correlation features can be extracted through data mining techniques such as association rule learning algorithms. It should be noted that this analysis should not only consider the immediate impact but also the lag effect, because the pressure change may affect the power supply stability after a certain period of time. Support Vector Machine (SVM) is an effective classification algorithm that can be used to distinguish between stable and unstable states of power supply distribution. When training the SVM model, the Radial Basis Function (RBF) can be selected as the kernel function, and the hyperparameters C and γ can be optimized through the cross-validation method. For example, the range of C can be set as [0.1, 1, 10, 100], and the range of γ can be set as [0.01, 0.1, 1, 10], and the best parameter combination can be found through grid search. The optimal power distribution model can be constructed using the logistic regression algorithm. Specifically, the internal pressure, force data, etc. can be used as independent variables, and the power supply stability can be used as the dependent variable (0 represents unstable, 1 represents stable). The model parameters are solved through the maximum likelihood estimation method to obtain a model that can predict the probability of power supply stability. The advantage of this method is that it can quantify the influence degree of different factors on the power supply stability. When adjusting the power distribution scheme in real time, the model prediction results and preset rules can be combined. For example, when the model predicts that the probability of power supply instability exceeds 80%, the power reallocation mechanism is triggered. The specific reallocation strategy can be based on priorities, allocating more power to critical devices while reducing the power supply to non-critical devices. This dynamic adjustment method can improve the overall stability and reliability of the system. It should be emphasized that this data-driven power supply distribution optimization method has strong adaptability and scalability. With the accumulation of data and the iteration of the model, the system can continuously learn and improve to adapt to different working environments and device configurations. This not only improves the power supply efficiency but also extends the device life and reduces system failures caused by unstable power supply.

[0066] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than limiting the protection scope of the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the essence and scope of the technical solutions of the present invention.

Claims

1. A doll with intelligent simulation eyes, characterized in that: It includes a support body; the support body is provided with simulation eyes and an air pump; the simulation eyes are LCD screens; the air pump is electrically connected to the LCD screens; an air inflation cavity is arranged inside the support body; the output end of the air pump is communicated with the air inflation cavity.

2. The doll with intelligent simulation eyes according to claim 1, wherein: A PVC sheet is arranged between the LCD screen and the support body.

3. The doll with intelligent simulation eyes according to claim 2, characterized in that: The PVC sheet extends to be provided with a connecting seat; the connecting seat is detachably connected with a waterproof rear cover; a containing cavity is formed between the connecting seat and the waterproof rear cover; the LCD screen is arranged in the containing cavity; the PVC sheet is provided with a display channel communicated with the containing cavity in a penetrating manner.

4. The doll with intelligent simulation eyes according to claim 3, characterized in that: A waterproof silica gel sheet is arranged between the LCD screen and the connecting seat; The PVC sheet is connected with the support body by glue and / or sewing.

5. A doll with intelligent simulation eyes according to claim 1, characterized in that: The doll with intelligent simulation eyes further includes a rotating disk; the support body is arranged on the rotating disk.

6. The doll with intelligent simulation eyes according to claim 1, characterized in that: It includes the following steps: S101. Obtain the real-time data during the operation of the air pump to obtain the dynamic correlation data of load fluctuation and power supply distribution; S102. Judge the output state of the air pump according to the dynamic correlation data and adjust the voltage output range of the air pump; S103. Judge the power supply stability of the LCD screen according to the adjusted voltage output range and adopt a voltage stabilizing module to compensate and adjust the power supply line; S104. Adjust the installation structure of the LCD screen according to the internal pressure change of the air inflation cavity; S105. Judge the power supply distribution stability according to the force data of the adjusted installation structure and generate an optimal power distribution model.

7. The doll with intelligent simulation eyes according to claim 6, characterized in that: The obtaining the real-time data during the operation of the air pump to obtain the dynamic correlation data of load fluctuation and power supply distribution includes: obtaining the current value, air pressure value and LCD screen power supply voltage value during the operation of the air pump through a sensor, processing the digital data by time series analysis, determining the frequency component and dynamic correlation intensity of load fluctuation, determining the influence coefficient of voltage stability on power supply distribution through regression analysis, and generating a classification model result by using a support vector machine algorithm.

8. The doll with intelligent simulation eyes according to claim 6, wherein: The judging the output state of the air pump according to the dynamic correlation data and adjusting the voltage output range of the air pump includes: extracting the output value from the dynamic correlation data set and comparing it with a preset threshold value. If it exceeds the preset range, obtain the target voltage output range value, adjust the voltage parameter of the air pump drive module, and optimize the control parameter by using a random forest algorithm to generate stable output state data.

9. The doll with intelligent simulation eyes according to claim 6, characterized in that: The judging the power supply stability of the LCD screen according to the adjusted voltage output range and adopting a voltage stabilizing module to compensate and adjust the power supply line includes: collecting the adjusted voltage output range and comparing it with the LCD screen power supply demand threshold value, extracting the characteristics of the insufficient stability state, obtaining the voltage stabilizing module adjustment parameter from a preset module, optimizing the deviation characteristics by using a support vector machine algorithm, updating the voltage stabilizing module control logic, and generating the voltage output data after stabilization.

10. A doll with intelligent simulation eyes according to claim 6, characterized in that: The installation structure for adjusting the LCD screen according to the internal pressure change of the inflatable cavity includes: obtaining the real-time data of the internal pressure of the inflatable cavity, processing the pressure change time series data through a convolutional neural network, determining the spatial extrusion quantization index, predicting the deformation amount using a regression algorithm, simulating the stress distribution through finite element analysis, verifying the stability of the adjustment scheme, and obtaining the optimized installation structure parameters; The method for judging the stability of power supply distribution according to the force data of the adjusted installation structure and generating an optimal power distribution model includes: analyzing the internal pressure change trend and force data of the inflatable cavity, determining the fluctuation conditions and threshold ranges, training the historical data classification through a support vector machine, adjusting the hyperparameters to generate a classification model, and using logistic regression to analyze the historical power distribution data to generate an optimal power distribution model and output the optimization results.

Images